Related papers: Certification of Speaker Recognition Models to Add…

Robustness certification, which aims to formally certify the predictions of neural networks against adversarial inputs, has become an integral part of important tool for safety-critical applications. Despite considerable progress, existing…

Training speaker-discriminative and robust speaker verification systems without explicit speaker labels remains a persistent challenge. In this paper, we propose a novel self-supervised speaker verification approach, Self-Distillation…

Training speaker-discriminative and robust speaker verification systems without explicit speaker labels remains a persisting challenge. In this paper, we propose a new self-supervised speaker verification approach, Self-Distillation…

Self-supervised learning (SSL) methods which learn representations of data without explicit supervision have gained popularity in speech-processing tasks, particularly for single-talker applications. However, these models often have…

Noise robustness remains a critical challenge for deploying neural speech codecs in real-world acoustic scenarios where background noise is often inevitable. A key observation we make is that even slight input noise perturbations can cause…

We study the capabilities of speech processing systems trained simply to predict large amounts of transcripts of audio on the internet. When scaled to 680,000 hours of multilingual and multitask supervision, the resulting models generalize…

As audio deepfakes transition from research artifacts to widely available commercial tools, robust biometric authentication faces pressing security threats in high-stakes industries. This paper presents a systematic empirical evaluation of…

The ResNet-based architecture has been widely adopted to extract speaker embeddings for text-independent speaker verification systems. By introducing the residual connections to the CNN and standardizing the residual blocks, the ResNet…

Environmental noises and reverberation have a detrimental effect on the performance of automatic speech recognition (ASR) systems. Multi-condition training of neural network-based acoustic models is used to deal with this problem, but it…

Robust speaker recognition, including in the presence of malicious attacks, is becoming increasingly important and essential, especially due to the proliferation of several smart speakers and personal agents that interact with an…

Randomized smoothing, a method to certify a classifier's decision on an input is invariant under adversarial noise, offers attractive advantages over other certification methods. It operates in a black-box and so certification is not…

Discretized representations of speech signals are efficient alternatives to continuous features for various speech applications, including automatic speech recognition (ASR) and speech language models. However, these representations, such…

Speaker adaptation techniques provide a powerful solution to customise automatic speech recognition (ASR) systems for individual users. Practical application of unsupervised model-based speaker adaptation techniques to data intensive…

The goal of this paper is to learn robust speaker representation for bilingual speaking scenario. The majority of the world's population speak at least two languages; however, most speaker recognition systems fail to recognise the same…

Speech utterances recorded under differing conditions exhibit varying degrees of confidence in their embedding estimates, i.e., uncertainty, even if they are extracted using the same neural network. This paper aims to incorporate the…

Visual signals can enhance audiovisual speech recognition accuracy by providing additional contextual information. Given the complexity of visual signals, an audiovisual speech recognition model requires robust generalization capabilities…

The performance of speaker verification systems degrades when vocal effort conditions between enrollment and test (e.g., shouted vs. normal speech) are different. This is a potential situation in non-cooperative speaker verification tasks.…

Recently, fine-tuning large pre-trained Transformer models using downstream datasets has received a rising interest. Despite their success, it is still challenging to disentangle the benefits of large-scale datasets and Transformer…

Data augmentation (DA) has played a pivotal role in the success of deep speaker recognition. Current DA techniques primarily focus on speaker-preserving augmentation, which does not change the speaker trait of the speech and does not create…

This paper presents Conformer-1, an end-to-end Automatic Speech Recognition (ASR) model trained on an extensive dataset of 570k hours of speech audio data, 91% of which was acquired from publicly available sources. To achieve this, we…